Issue 2 • Date June 2009
Special Issue on 3D Face ProcessingPage(s): 47 - 48| PDF (70 KB)
The authors present an adaptive colour classification method as well as specialised low-level image processing algorithms. With this approach the authors achieve high-quality 3D reconstructions with a single-shot structured light system without the need of dark laboratory environments. The main focus of the presented work lies in the enhancement of the robustness with respect to environment illumination, colour cross-talk, reflectance characteristics of the scanned face etc. For this purpose the colour classification is made adaptive to the characteristics of the captured image to compensate for such distortions. Further improvements are concerned with enhancing the quality of the resulting 3D models. Therefore the authors replace the typical general-purpose image preprocessing with specialised low-level algorithms performing on raw photo sensor data. The presented system is suitable for generating high-speed scans of moving objects because it relies only on one captured image. Furthermore, due to the adaptive nature of the used colour classifier, it generates high-quality 3D models even under perturbing light conditions. View full abstract»
The authors apply partial least squares regression to predict three-dimensional (3D) face shape from a single image. PLS describes the relationship between independent (intensity images) and dependent (3D shape) variables by seeking directions in the space of independent variables that are associated with large variations in the space of dependent variables. We use this idea to construct statistical models of intensity and 3D shape that capture strongly linked variations in both spaces. This decomposition leads to the construction of two different models that capture common variations in 3D shape and intensity. Using the intensity model, a set of parameters is obtained from out-of-training intensity examples. These intensity parameters can then be used directly in the 3D shape model to approximate facial shape. Experiments show that prediction is achieved with reasonable accuracy, improving results obtained through canonical correlation analysis. View full abstract»
A practical identification system based on 3D face scanning is presented. The speed of comparing a probe scan to the gallery is enabled by scan normalisation followed by extraction of higher level features. Our canonical face depth map (CFDM) is a standardised representation for three-dimensional (3D) face data in a face-based coordinate system. Our experiments demonstrate that the CFDM normalisation algorithm is (a) robust to noise and occlusion, (b) significantly reduces storage requirements and thus I/O time, and (c) improves the efficiency of face recognition algorithms. Producing the CFDM takes less than a second on a desktop for 320 times 240 rangel scans. Current 3D scanning and matching methods are too slow for person identification, even for a watch list of only a few hundred face models. Transforming scanned 3D faces into CFDM format enables a probe scan to be matched to hundreds or thousands of gallery scans in a fewtimesseconds on a commodity computer. The best results achieved so far are a rank-1 recognition rate of 98.2% and a speed of 1900 face matches per second. Extrapolating these results suggests that multistage systems could achieve even better performance on even larger galleries. View full abstract»
A method for robustly tracking and estimating the face pose of a person using stereo vision is presented. The method is invariant to identity and does not require previous training. A face model is automatically initialised and constructed online: a fixed point distribution is superposed over the face when it is frontal to the cameras, and several appropriate points close to those locations are chosen for tracking. Using the stereo correspondence of the cameras, the three-dimensional (3D) coordinates of these points are extracted, and the 3D model is created. The 2D projections of the model points are tracked separately on the left and right images using SMAT. RANSAC and POSIT are used for 3D pose estimation. Head rotations up to plusmn45deg are correctly estimated. The approach runs in real time. The purpose of this method is to serve as the basis of a driver monitoring system, and has been tested on sequences recorded in a moving car. View full abstract»
Aims & Scope
IET Computer Vision seeks original research papers in a wide range of areas of computer vision. The vision of the journal is to publish the highest quality research work that is relevant and topical to the field, but not forgetting those works that aim to introduce new horizons and set the agenda for future avenues of research in Computer Vision.